Early detection of breast cancer through the mammography screening programme
Conditions
Interventions
Group 1: In subprojects 1 and 2, at least 200,000 anonymised mammograms taken as part of the mammography screening programme are analysed retrospectively.
In subproject 3, interviews are conducted wi
Sponsors
Uniklinik RWTH Aachen, Klinik für Diagnostische und Interventionelle Radiologie
Eligibility
Sex/Gender
Female
Age
50 Years to 75 Years
Inclusion criteria
Inclusion criteria: In subproject 1+2: 1. Women did participate at German Mammography Screening in the past 2. Women were at least 50 years old at time of participation 3. Women did not have any clinical signs of breast cancer at time of screening 4. Follow-up information of at least two negative subsequent mammography screening rounds or cancer detection by a subsequent mammography screening or cancer detection outside the program In subproject 3: 1. Women currently participating in the mammogram screening programme in Germany
Exclusion criteria
Exclusion criteria: In subproject 1+2: 1. Women who have refused to report to the cancer registry In subproject 3: 1. Women who are not able to give consent 2. Women who are not able to take part in the structured interviews due to mental reasons
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| The aim of the study is to validate a novel deep learning algorithm that helps to identify women who have an increased risk of having a mammographically occult breast cancer, i.e. a risk of having a false-negative mammogram. The predictive power of the algorithm is compared with that of established risk prediction based on mammographically determined breast tissue density alone. By developing, calibrating and validating decision analytic modelling, the effectiveness, risk-benefit ratio and cost-effectiveness of different potential risk-adjusted screening methods for women at increased risk of breast cancer will be evaluated and compared. | — |
Countries
Germany
Outcome results
None listed